Sentiment Analysis in Public Health Crisis Applications: A Conceptual Framework
Keywords:
Sentiment Analysis, Support Vector Machine, Naïve Bayes, Random Forest, K-Nearest NeighbourAbstract
Sentiment analysis, also known as opinion mining, is a Natural Language Processing (NLP) technique. It predicts people's opinions on products or services offered, whether positive, negative, or neutral. As a result, the outcome may assist an organisation in making better decisions. Nevertheless, sentiment analysis in the context of public health crisis apps is still new. A complete framework for the sentiment analysis model in this area is still lacking. In this paper, a comprehensive framework regarding sentiment analysis on user reviews of a public health crisis is proposed. The proposed framework represents a classification model that works as a complete guide for developers, researchers, and firms to create and deploy machine learning models more quickly and efficiently in the field of public health crisis apps. It starts with the data collection of user reviews and is followed by data labelling. The third stage is data pre-processing, where the data will be cleaned to improve the quality of the data and classification effectiveness. The fourth stage is feature extraction, in which the adjectives of the cleaned data will be identified by the TF-IDF technique. The fifth stage is data training and testing. Supervised machine learning classifiers, which are Support Vector Machine (SVM), Naïve Bayes (NB), Random Forest (RF), and K-Nearest Neighbour (KNN) will be used to perform data training and testing. The last stage is performance evaluation and comparison. This stage identifies the best classifier based on the measurement parameters. Based on the experiment conducted, the framework is fit for this study since the experiment produces a good score of the F-measure. The framework will benefit developers, firms, and researchers by assisting them to model their sentiment analysis work
References
E. Fersini, Sentiment Analysis in Social Networks. 2017.
World Health Organization, Communicating Risk in Public Health Emergencies. 2017. [Online]. Available:https://apps.who.int/iris/bitstream/handle/10665/259807/9789241550208-eng.pdf?sequence=2
D. S. and L. Buis, “Mobile Health Apps for Medical Emergencies: Systematic Review,” Journal of Medical Internet Research, 2020.
P. H. O. archive pageTate R.-M. archive pageBobbie Johnson, “A flood of coronavirus apps are tracking us. Now it’s time to keep track of them.No Title,” MIT Technology Review, 2020.
E. Gabarron, E. Dorronzoro, O. Rivera-Romero, and R. Wynn, “Diabetes on Twitter: A Sentiment Analysis,” Journal of Diabetes Science and Technology, vol. 13, no. 3, pp. 439–444, May 2019, doi: 10.1177/1932296818811679.
R. R. Pai and S. Alathur, “Assessing mobile health applications with twitter analytics,” International Journal of Medical Informatics, vol. 113, pp. 72–84, May 2018, doi: 10.1016/j.ijmedinf.2018.02.016.
K. Rekanar et al., “Sentiment Analysis of User Feedback on the HSE Contact Tracing App,” 2020, doi: 10.21203/rs.3.rs-96174/v1.
F. Greaves, D. Ramirez-Cano, C. Millett, A. Darzi, and L. Donaldson, “Use of sentiment analysis for capturing patient experience from free-text comments posted online,” Journal of Medical Internet Research, vol. 15, no. 11, 2013, doi: 10.2196/jmir.2721.
J. Du, J. Xu, H. Song, X. Liu, and C. Tao, “Optimization on machine learning based approaches for sentiment analysis on HPV vaccines related tweets,” Journal of Biomedical Semantics, vol. 8, no. 1, Mar. 2017, doi: 10.1186/s13326-017-0120-6.
Q. Cheng, T. M. Li, C. L. Kwok, T. Zhu, and P. S. Yip, “Assessing suicide risk and emotional distress in Chinese social media: A text mining and machine learning study,” Journal of Medical Internet Research, vol. 19, no. 7, 2017, doi: 10.2196/jmir.7276.
S. Yadav, A. Ekbal, S. Saha, and P. Bhattacharyya, “Medical Sentiment Analysis using Social Media: Towards building a Patient Assisted System.” [Online]. Available: http://sideeffects.embl.de/
S. Park and J. Woo, “Gender classification using sentiment analysis and deep learning in a health web forum,” Applied Sciences (Switzerland), vol. 9, no. 6, 2019, doi: 10.3390/app9061249.
O. Oyebode, F. Alqahtani, and R. Orji, “Using Machine Learning and Thematic Analysis Methods to Evaluate Mental Health Apps Based on User Reviews,” IEEE Access, vol. 8, pp. 111141–111158, 2020, doi: 10.1109/ACCESS.2020.3002176.
T. Puyalnithi, M. V. V, and A. Singh, “Comparison of Performance of Various Data Classification Algorithms with Ensemble Methods Using RAPIDMINER,” vol. 6, no. 5, pp. 1–6, 2016.
W. R. Hersh et al., “Recommendations for the use of operational electronic health record data in comparative effectiveness research,” EGEMS, vol. 1, no. 1, 2013.
S. McIlroy, N. Ali, H. Khalid, and A. E. Hassan, “Analyzing and automatically labelling the types of user issues that are raised in mobile app reviews,” Empirical Software Engineering, vol. 21, no. 3, pp. 1067–1106, 2016, doi: 10.1007/s10664-015-9375-7.
R. M. Duwairi, M. Alfaqeh, M. Wardat, and A. Alrabadi, “Sentiment analysis for Arabizi text,” 2016 7th International Conference on Information and Communication Systems, ICICS 2016, no. April, pp. 127–132, 2016, doi: 10.1109/IACS.2016.7476098.
P. Pang and L. Lee, “Sentimental education: extract subjective sentences from reviews,” ACL ’04 Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p. 8, 2004, [Online]. Available: file://localhost/Volumes/alexvanvenrooij 1/Elektronische Artikelen/Papers/Unknown/2004-8.pdf
Ryan Miller, “Data Preprocessing: what is it and why is important,” Dec. 13, 2019.
K. Mouthami, K. N. Devi, and V. M. Bhaskaran, “Sentiment analysis and classification based on textual reviews,” 2013 International Conference on Information Communication and Embedded Systems, ICICES 2013, pp. 271–276, 2013, doi: 10.1109/ICICES.2013.6508366.
S. Singh, A. Pareek, and A. Sharma, “Twitter Sentiment Analysis using Rapid Miner Tool,” International Journal of Computer Applications, vol. 177, no. 16, pp. 44–50, 2019, doi: 10.5120/ijca2019919604.
P. Bafna, D. Pramod, and A. Vaidya, “Document clustering: TF-IDF approach,” in International Conference on Electrical, Electronics, and Optimization Techniques, ICEEOT 2016, Nov. 2016, pp. 61–66. doi: 10.1109/ICEEOT.2016.7754750.
A. Madasu and S. E, “A Study of Feature Extraction techniques for Sentiment Analysis,” Jun. 2019, [Online]. Available: http://arxiv.org/abs/1906.01573
Sajid Lhessani, “What is the difference between training and test dataset?,” Sep. 28, 2019.
E. Zuo, H. Zhao, B. Chen, and Q. Chen, “Context-Specific Heterogeneous Graph Convolutional Network for Implicit Sentiment Analysis,” IEEE Access, vol. 8, pp. 37967–37975, 2020, doi: 10.1109/ACCESS.2020.2975244.
M. A. Ghaderi, N. Yazdani, B. Moshiri, and M. Tayefeh Mahmoudi, “A new approach for text feature selection based on OWA operator,” 2010 5th International Symposium on Telecommunications, IST 2010, pp. 579–583, 2010, doi: 10.1109/ISTEL.2010.5734091.
G. N. A. S. Whitelaw C, “Using appraisal groups for sentiment analysis,” 2005, pp. 625–631.
X. Yiming Yang, “A re-examination of text categorization methods,” 1999, pp. 42–49.
